← Back to community benchmarks

Qwen3.6-27B-oQ8-mtp

M3 Ultra (60c) · 96 GB · 8bit · 2026-05-09
Performance
16k
tokens
308.6
PP tok/s
28.6
TG tok/s
53093
TTFT (ms)
32.8
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 96 GB
GPU Cores 60
Software
oMLX v0.3.9.dev1
macOS macOS 26.4
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 296.2 31.5 28.8 GB view
4k 318.7 31.9 30.3 GB view
8k 317.2 30.6 31.3 GB view
16k 308.6 28.6 32.8 GB current
32k 288.6 26.9 35.8 GB view
64k 221.5 22.1 41.8 GB view